CN107437073A - Face skin quality analysis method and system based on deep learning with generation confrontation networking - Google Patents
Face skin quality analysis method and system based on deep learning with generation confrontation networking Download PDFInfo
- Publication number
- CN107437073A CN107437073A CN201710590573.8A CN201710590573A CN107437073A CN 107437073 A CN107437073 A CN 107437073A CN 201710590573 A CN201710590573 A CN 201710590573A CN 107437073 A CN107437073 A CN 107437073A
- Authority
- CN
- China
- Prior art keywords
- skin
- face
- networking
- analyzed
- deep learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 75
- 230000006855 networking Effects 0.000 title claims abstract description 37
- 238000013135 deep learning Methods 0.000 title claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 36
- 230000001815 facial effect Effects 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 9
- 210000000056 organ Anatomy 0.000 claims abstract description 7
- 230000003993 interaction Effects 0.000 claims description 14
- 239000002537 cosmetic Substances 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 210000001508 eye Anatomy 0.000 claims description 5
- 210000001061 forehead Anatomy 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 5
- 238000006467 substitution reaction Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 206010013786 Dry skin Diseases 0.000 description 3
- 241000700647 Variola virus Species 0.000 description 3
- 210000003467 cheek Anatomy 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000037336 dry skin Effects 0.000 description 3
- 239000011148 porous material Substances 0.000 description 3
- 230000037303 wrinkles Effects 0.000 description 3
- 235000002673 Dioscorea communis Nutrition 0.000 description 2
- 241000544230 Dioscorea communis Species 0.000 description 2
- 206010027146 Melanoderma Diseases 0.000 description 2
- 208000035753 Periorbital contusion Diseases 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 210000001331 nose Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002939 deleterious effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- 208000001491 myopia Diseases 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
Face skin quality analysis method and system provided by the invention based on deep learning with generation confrontation networking, including：Image acquisition step：Obtain facial image to be analyzed；Divide block step：The facial image to be analyzed is analyzed, skin block is divided to the facial image to be analyzed according to each organ；Analytical procedure：Different skin analysers is imported in different skin blocks, skin analyser is used to analyze the skin condition in corresponding skin block；As a result step is exported：Export the analysis result of all skin analysers.This method obtains in face skin quality data be not easy, be distributed and be regardless of in the case of, auxiliary information is produced through generation confrontation networking, the application analyzed using the model substitution traditional images Processing Algorithm of deep learning in skin quality, it can be analyzed for face skin detail, the skin of different qualities is directed to reference to generation confrontation networking, the generation of training data is done using limited data, obtains more preferable training effect.
Description
Technical field
The invention belongs to technical field of image processing, and in particular to the face skin based on deep learning with generation confrontation networking
Matter analysis method and system.
Background technology
Over the past several decades, the correlative study of existing many deep learnings, but because required training data is huge, therefore permitted
More researchs can not be realized.In recent years, due to the development of big data and internet, researcher can obtain substantial amounts of training money
Material, therefore deep learning technology starts to develop rapidly.With being in fashion for the short-sighted frequencies of live Dian, the business application that face effect Dian is compiled
It is put into substantial amounts of sight and research data.
Analyzed however, current human face analysis research is rare for skin detail, due to face skin data for compared with
Privacy Dian involves the part of medical act, and data is obtained and is not easy, the multi-purpose traditional images processing for being not required to mass data of past method
Technology, its effect is limited, and therefore, how to carry out the analysis of people's face skin under limited data using deep learning turns into one
Important research topic.
The content of the invention
For in the prior art the defects of, the present invention provides the face skin quality point based on deep learning with generation confrontation networking
Method and system are analysed, can be analyzed for face skin detail, the skin of different qualities is directed to reference to generation confrontation networking,
The generation of training data is done using limited data, obtains more preferable training effect.
A kind of face skin quality analysis method based on deep learning with generation confrontation networking, including：
Image acquisition step：Obtain facial image to be analyzed；
Divide block step：The facial image to be analyzed is analyzed, according to each organ to the people to be analyzed
Face image divides skin block；
Analytical procedure：Different skin analysers is imported in different skin blocks, skin analyser is used for analysis pair
Skin condition in the skin block answered；
As a result step is exported：Export the analysis result of all skin analysers.
Preferably, in the division block step, by the detecting of face key point and skin block cutting algorithm, to described
Facial image to be analyzed divides skin block.
Preferably, in the division block step, the skin block of division includes forehead, cheek, nose, eyes and mouth
Bar.
Preferably, in the analytical procedure, the training method of the skin analyser includes：
Obtain and treat training data, establish face data bank；
Generation confrontation networking, to treating that training data learns in the face data bank, learns to treat people in training data
The texture message of face, produce training data；
Training data is filtered, obtains and is distributed average training data, form the skin analyser.
Preferably, in the result output step, the analysis result of the skin analyser is shown by display screen.
A kind of face skin quality analysis system based on deep learning with generation confrontation networking, depth is based on suitable for above-mentioned
The face skin quality analysis method with generation confrontation networking is practised, including：
Image collection module：For obtaining facial image to be analyzed；
Divide block module：Analyzed for treating the analysis facial image, treated point to described according to each organ
Analyse facial image division skin block；
Analysis module：For different skin analysers to be imported in different skin blocks, skin analyser is used to divide
Skin condition in skin block corresponding to analysis；
As a result output module：For exporting the analysis result of all skin analysers.
Preferably, described image acquisition module includes camera, and the facial image to be analyzed is obtained by camera shooting
.
Preferably, it is described that mirror or shifting are arranged at based on deep learning and the face skin quality analysis system at generation confrontation networking
In dynamic terminal；The result output module includes the display screen being arranged on mirror or mobile terminal, the skin analyser
Analysis result is shown by display screen.
Preferably, in addition to：Voice interaction module and network communication module；
The voice interaction module is used to connect network by the network communication module, and voice interaction module is used to play
The analysis result of the skin analyser, it is additionally operable to realization and is interacted with the real-time online of user.
Preferably, the voice interaction module interacted with the real-time online of user including：Cosmetic or skin care suggestion are provided, looked into
Ask same day user's travel schedule, the inquiry same day it is meteorological or with user's chat conversations.
As shown from the above technical solution, the face skin quality point provided by the invention based on deep learning with generation confrontation networking
Method and system are analysed, is obtained in face skin quality data in the case of being not easy, be distributed and be regardless of, is produced and aid in through generation confrontation networking
Data, the application analyzed using the model substitution traditional images Processing Algorithm of deep learning in skin quality, can be directed to people's face skin
Details is analyzed, and the skin of different qualities is directed to reference to generation confrontation networking, the life of training data is done using limited data
Into obtaining more preferable training effect.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art
The required accompanying drawing used is briefly described in embodiment or description of the prior art.In all of the figs, similar element
Or part is typically identified by similar reference.In accompanying drawing, each element or part might not be drawn according to the ratio of reality.
Fig. 1 is the flow chart of image acquisition step and division block step in face skin quality analysis method.
Fig. 2 is the classification chart of skin analyser in face skin quality analysis method.
Fig. 3 is the flow chart of analytical procedure in face skin quality analysis method.
Fig. 4 is the structured flowchart of voice interaction module in face skin quality analysis system.
Embodiment
The embodiment of technical solution of the present invention is described in detail below in conjunction with accompanying drawing.Following examples are only used for
Clearly illustrate technical scheme, therefore be only used as example, and the protection model of the present invention can not be limited with this
Enclose.It should be noted that unless otherwise indicated, technical term or scientific terminology used in this application are should be belonging to the present invention
The ordinary meaning that art personnel are understood.
Embodiment：
With the development of cell phone application and internet, produce numerous images and compile live application.Current application is mostly to make
With image filters or textures beautification picture, few application that analysis and optimization is carried out for people's face skin.Therefore, the present invention wants base
In computer vision algorithm, for face skin detail (such as small pox, wrinkle, black mole, pore are thick, skin is glossy, dry skin,
Livid ring around eye etc.) analyzed.
Makeups intelligent assistant is also the red as fire project of current AI industry, but makeups intelligent assistant in life should
With being often not firm need.For women, most women can spend dozens of minutes before mirror or through running gear daily
Camera arranges appearance, and this is just needed for life, therefore is detected through skin quality, is integrated makeups intelligent assistant, is one very good
Business application.It is that this is of the invention by integrating makeups intelligent assistant, designs a makeups intelligent assistant.Because deep learning needs
A large amount of training data, but skin detail data is obtained and is not easy, therefore the present invention is also directed to different qualities with reference to generation confrontation networking
Skin, do the generation of training data using limited data, help the present invention to obtain more preferable training effect.
One is proposed in the present invention framework of skin skin quality analysis is carried out using deep learning, while solve skin skin quality instruction
Practice data and obtain the problem of being not easy, and design intelligent assistant's product.This framework is divided into three phases, and the first stage utilizes face
Detecting, the detecting of face key point, skin carry out skin area positioning, thereby distinguish the different block of face subsequently to be divided
Analysis.Second stage carries out the Detailled analysis of skin, exports the analysis result of this area skin.Phase III is interactive with user
Makeups intelligent assistant.
A kind of face skin quality analysis method based on deep learning with generation confrontation networking, as Figure 1-4, including：
Image acquisition step：Obtain facial image to be analyzed；
Divide block step：The facial image to be analyzed is analyzed, according to each organ to the people to be analyzed
Face image divides skin block；
Analytical procedure：Different skin analysers is imported in different skin blocks, skin analyser is used for analysis pair
Skin condition in the skin block answered；
As a result step is exported：Export the analysis result of all skin analysers.In the result output step, pass through display
Screen shows the analysis result of the skin analyser.
This method obtains in face skin quality data be not easy, be distributed and be regardless of in the case of, it is auxiliary through generation confrontation networking generation
Data is helped, the application analyzed using the model substitution traditional images Processing Algorithm of deep learning in skin quality, people's face can be directed to
Skin details is analyzed, and the skin of different qualities is directed to reference to generation confrontation networking, training data is done using limited data
Generation, obtains more preferable training effect.
It is first stage, described to divide in block step, pass through the detecting of face key point and the cutting calculation of skin block of maturation
Method, skin block is divided to the facial image to be analyzed.The skin block of division includes forehead, left and right cheek, nose, left and right
Eye circumference is enclosed, arround face.Because the analysis emphasis of each block skin is different, thus different skin analyser importings is different
In skin block, skin analyser is used to analyze the skin condition in corresponding skin block.For example, the block of left and right cheek is led
Enter the graders such as glossy wrinkle, small pox, blackspot, skin, dry skin, pore be thick, skin around eyes block, import black eye
Circle, pouch grader.
Second stage, it is the training of every skin analysis grader, this part is the core of the present invention, utilizes convolutional Neural
Each skin correlation classifier of network training, for example, wrinkle, small pox, blackspot, skin are glossy, dry skin, pore are thick, black eye
Circle, pouch etc..Because skin thin portion data is for fear of individual privacy, it is not easy to obtain, the facial image got by internet is more
For the image beautified, the good data of skin, the data of less skin difference, this data injustice were typically only collected
The phenomenon of weighing apparatus, deleterious effect can be caused to the training of grader, therefore the present invention obtains and treats training data, establishes face data
Storehouse；Generation confrontation networking, to treating that training data learns in the face data bank, learns to treat the line of face in training data
Message is managed, produces training data；Training data is filtered, can be manual type filtering, obtain and be distributed average training data, be formed
The skin analyser.
Phase III, using the result of skin quality analysis, with the makeups intelligent assistant of makeups intelligent assistant Integration Design one, i.e. base
The face skin quality analysis system at networking is resisted with generation in deep learning, resisted suitable for above-mentioned based on deep learning and generation
The face skin quality analysis method at networking, including：
Image collection module：For obtaining facial image to be analyzed；
Divide block module：Analyzed for treating the analysis facial image, treated point to described according to each organ
Analyse facial image division skin block；
Analysis module：For different skin analysers to be imported in different skin blocks, skin analyser is used to divide
Skin condition in skin block corresponding to analysis；
As a result output module：For exporting the analysis result of all skin analysers.
This product is presented with two kinds of entity carriers：First, Intelligent mirror, two, mobile phone application.Described image acquisition module includes
Camera, the facial image to be analyzed are shot by camera and obtained.
It is described that mirror or mobile terminal are arranged at based on deep learning and the face skin quality analysis system at generation confrontation networking
In；The result output module includes the display screen being arranged on mirror or mobile terminal, the analysis knot of the skin analyser
Fruit is shown by display screen.
Also include：Voice interaction module and network communication module；
The voice interaction module is used to connect network by the network communication module, and voice interaction module is used to play
The analysis result of the skin analyser, it is additionally operable to realization and is interacted with the real-time online of user.
The voice interaction module interacted with the real-time online of user including：Cosmetic or skin care suggestion, the inquiry same day are provided
User's travel schedule, the inquiry same day it is meteorological or with user's chat conversations.
This intelligent assistant is provided with a camera, and (Intelligent mirror is projected in mirror in itself, and mirror is provided with aobvious with a screen
Display screen, mobile phone application are then superimposed on a display screen), and with phonetic function connection internet.When camera is detected and analyzes face
After portion's skin, analysis result can be presented on screen, and user is informed using speech method, and and user interaction,
It is proposed cosmetic Dian maintenance suggestions, it is also possible to user arrange appearance simultaneously, the stroke on user's same day is shown on screen
Table is meteorological with the same day, promotes user's stickiness.The systematic difference illustrated below.
Application scenarios one：Dresser in family
Using Intelligent mirror as carrier, dresser at home can be put, user go out before when mirror prefinishing appearance, this is beautiful
Adornment intelligent assistant can analyze user's skin quality, through makeups intelligent assistant, speech-sound intelligent assistant make up, maintenance suggestion, and prompt
Work as daily travel.
Application scenarios two：Cell phone application
Using cell phone application as carrier, user can confirm the appearance of oneself and skin quality shape when commuting using mobile phone camera
Condition, makeups intelligent assistant can provide suggestion and decide whether to refine the make-up, and remind ensuing stroke simultaneously.
Application scenarios three：Market (such as department store's special counter)
Using Intelligent mirror as carrier, department store's cosmetic counter is positioned over, customer can look in the mirror before special counter, this makeup
Intelligent assistant can analyze customer face skin quality situation, the cosmetics or skin care products for recommending customer to be adapted to, and can line special counter visitor
Family system, inquire about the past consumer record of customer automatically with reference to human face recognition, understand the usual cosmetics of customer, skin care products brand
With buying situation, make and more accurately suggesting.
Finally it should be noted that：Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations；To the greatest extent
The present invention is described in detail with reference to foregoing embodiments for pipe, it will be understood by those within the art that：Its according to
The technical scheme described in foregoing embodiments can so be modified, either which part or all technical characteristic are entered
Row equivalent substitution；And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology
The scope of scheme, it all should cover among the claim of the present invention and the scope of specification.
Claims (10)
- A kind of 1. face skin quality analysis method based on deep learning with generation confrontation networking, it is characterised in that including：Image acquisition step：Obtain facial image to be analyzed；Divide block step：The facial image to be analyzed is analyzed, according to each organ to the face figure to be analyzed As division skin block；Analytical procedure：Different skin analysers is imported in different skin blocks, skin analyser is corresponding for analyzing Skin condition in skin block；As a result step is exported：Export the analysis result of all skin analysers.
- 2. the face skin quality analysis method based on deep learning with generation confrontation networking, its feature exist according to claim 1 In,In the division block step, by the detecting of face key point and skin block cutting algorithm, to the face to be analyzed Image divides skin block.
- 3. the face skin quality analysis method based on deep learning with generation confrontation networking, its feature exist according to claim 2 In,In the division block step, the skin block of division includes forehead, cheek, nose, eyes and face.
- 4. the face skin quality analysis method based on deep learning with generation confrontation networking, its feature exist according to claim 1 In,In the analytical procedure, the training method of the skin analyser includes：Obtain and treat training data, establish face data bank；Generation confrontation networking, to treating that training data learns in the face data bank, learns to treat face in training data Texture message, produce training data；Training data is filtered, obtains and is distributed average training data, form the skin analyser.
- 5. the face skin quality analysis method based on deep learning with generation confrontation networking, its feature exist according to claim 1 In,In the result output step, the analysis result of the skin analyser is shown by display screen.
- 6. a kind of face skin quality analysis system based on deep learning with generation confrontation networking, it is characterised in that suitable for right It is required that the 1 face skin quality analysis method based on deep learning with generation confrontation networking, including：Image collection module：For obtaining facial image to be analyzed；Divide block module：Analyzed for treating the analysis facial image, according to each organ to the people to be analyzed Face image divides skin block；Analysis module：For different skin analysers to be imported in different skin blocks, skin analyser is used for analysis pair Skin condition in the skin block answered；As a result output module：For exporting the analysis result of all skin analysers.
- 7. the face skin quality analysis system based on deep learning with generation confrontation networking, its feature exist according to claim 6 In,Described image acquisition module includes camera, and the facial image to be analyzed is shot by camera and obtained.
- 8. the face skin quality analysis system based on deep learning with generation confrontation networking, its feature exist according to claim 6 In described to be arranged at based on deep learning and the face skin quality analysis system at generation confrontation networking in mirror or mobile terminal；Institute The display screen that result output module includes being arranged on mirror or mobile terminal is stated, the analysis result of the skin analyser passes through Display screen is shown.
- 9. the face skin quality analysis system based on deep learning with generation confrontation networking, its feature exist according to claim 6 In, in addition to：Voice interaction module and network communication module；The voice interaction module is used to connect network by the network communication module, and voice interaction module is described for playing The analysis result of skin analyser, it is additionally operable to realization and is interacted with the real-time online of user.
- 10. the face skin quality analysis system based on deep learning with generation confrontation networking, its feature exist according to claim 9 In,The voice interaction module interacted with the real-time online of user including：Cosmetic or skin care suggestion, inquiry same day user are provided Travel schedule, the inquiry same day it is meteorological or with user's chat conversations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710590573.8A CN107437073A (en) | 2017-07-19 | 2017-07-19 | Face skin quality analysis method and system based on deep learning with generation confrontation networking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710590573.8A CN107437073A (en) | 2017-07-19 | 2017-07-19 | Face skin quality analysis method and system based on deep learning with generation confrontation networking |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107437073A true CN107437073A (en) | 2017-12-05 |
Family
ID=60460443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710590573.8A Pending CN107437073A (en) | 2017-07-19 | 2017-07-19 | Face skin quality analysis method and system based on deep learning with generation confrontation networking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107437073A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108171208A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| CN108324247A (en) * | 2018-01-29 | 2018-07-27 | 杭州美界科技有限公司 | A kind of designated position wrinkle of skin appraisal procedure and system |
| CN108363965A (en) * | 2018-01-29 | 2018-08-03 | 杭州美界科技有限公司 | A kind of distributed face state appraisal procedure |
| CN108354590A (en) * | 2018-01-29 | 2018-08-03 | 杭州美界科技有限公司 | A kind of face state appraisal procedure based on burst mode |
| CN108389185A (en) * | 2018-01-29 | 2018-08-10 | 杭州美界科技有限公司 | A kind of face state appraisal procedure |
| CN108399364A (en) * | 2018-01-29 | 2018-08-14 | 杭州美界科技有限公司 | A kind of face state appraisal procedure of major-minor camera setting |
| CN108553083A (en) * | 2018-01-29 | 2018-09-21 | 杭州美界科技有限公司 | A kind of face state appraisal procedure under voice instruction |
| CN108851833A (en) * | 2018-06-01 | 2018-11-23 | 辽宁工程技术大学 | Smart pier glass and its training method based on machine learning training algorithm |
| CN109101870A (en) * | 2018-06-15 | 2018-12-28 | 深圳市赛亿科技开发有限公司 | Intelligent mirror and its control method, computer readable storage medium |
| CN109523334A (en) * | 2018-08-30 | 2019-03-26 | 新我科技(广州)有限公司 | Box between a kind of cosmetics intelligent shopping guide system, cosmetics intelligent shopping guide method and intelligent cosmetic |
| CN109618045A (en) * | 2018-11-27 | 2019-04-12 | Oppo广东移动通信有限公司 | Electronic device, information-pushing method and Related product |
| CN109614900A (en) * | 2018-11-29 | 2019-04-12 | 深圳和而泰数据资源与云技术有限公司 | Image detecting method and device |
| CN109886881A (en) * | 2019-01-10 | 2019-06-14 | 中国科学院自动化研究所 | Face dressing minimizing technology |
| CN109919029A (en) * | 2019-01-31 | 2019-06-21 | 深圳和而泰数据资源与云技术有限公司 | Black eye kind identification method, device, computer equipment and storage medium |
| CN111524080A (en) * | 2020-04-22 | 2020-08-11 | 杭州夭灵夭智能科技有限公司 | Face skin feature identification method, terminal and computer equipment |
| CN111868742A (en) * | 2018-01-05 | 2020-10-30 | 莱雅公司 | Machine implemented facial health and beauty aid |
| WO2021078037A1 (en) * | 2019-10-22 | 2021-04-29 | 华为技术有限公司 | Facial skin detection method and apparatus |
| CN113576421A (en) * | 2021-09-10 | 2021-11-02 | 广州帕克西软件开发有限公司 | Intelligent skin measuring method and device |
| CN113887483A (en) * | 2021-10-19 | 2022-01-04 | 杭州颜云科技有限公司 | Face pore detection method based on deep neural network |
| CN113971823A (en) * | 2020-07-24 | 2022-01-25 | 华为技术有限公司 | Method and electronic device for appearance analysis |
| US11636600B1 (en) * | 2022-02-23 | 2023-04-25 | Lululab Inc. | Method and apparatus for detecting pores based on artificial neural network and visualizing the detected pores |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299011A (en) * | 2014-10-13 | 2015-01-21 | 吴亮 | Skin type and skin problem identification and detection method based on facial image identification |
| CN104732214A (en) * | 2015-03-24 | 2015-06-24 | 吴亮 | Quantification skin detecting method based on face image recognition |
| US20150347819A1 (en) * | 2014-05-29 | 2015-12-03 | Beijing Kuangshi Technology Co., Ltd. | Compact Face Representation |
| CN106469302A (en) * | 2016-09-07 | 2017-03-01 | 成都知识视觉科技有限公司 | A kind of face skin quality detection method based on artificial neural network |
-
2017
- 2017-07-19 CN CN201710590573.8A patent/CN107437073A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150347819A1 (en) * | 2014-05-29 | 2015-12-03 | Beijing Kuangshi Technology Co., Ltd. | Compact Face Representation |
| CN104299011A (en) * | 2014-10-13 | 2015-01-21 | 吴亮 | Skin type and skin problem identification and detection method based on facial image identification |
| CN104732214A (en) * | 2015-03-24 | 2015-06-24 | 吴亮 | Quantification skin detecting method based on face image recognition |
| CN106469302A (en) * | 2016-09-07 | 2017-03-01 | 成都知识视觉科技有限公司 | A kind of face skin quality detection method based on artificial neural network |
Non-Patent Citations (1)
| Title |
|---|
| 胡聪丛等: "深度神经网络的发展现状", 《电子技术与软件工程》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111868742A (en) * | 2018-01-05 | 2020-10-30 | 莱雅公司 | Machine implemented facial health and beauty aid |
| CN108171208A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| CN108399364A (en) * | 2018-01-29 | 2018-08-14 | 杭州美界科技有限公司 | A kind of face state appraisal procedure of major-minor camera setting |
| CN108324247A (en) * | 2018-01-29 | 2018-07-27 | 杭州美界科技有限公司 | A kind of designated position wrinkle of skin appraisal procedure and system |
| CN108389185A (en) * | 2018-01-29 | 2018-08-10 | 杭州美界科技有限公司 | A kind of face state appraisal procedure |
| CN108363965A (en) * | 2018-01-29 | 2018-08-03 | 杭州美界科技有限公司 | A kind of distributed face state appraisal procedure |
| CN108553083A (en) * | 2018-01-29 | 2018-09-21 | 杭州美界科技有限公司 | A kind of face state appraisal procedure under voice instruction |
| CN108354590A (en) * | 2018-01-29 | 2018-08-03 | 杭州美界科技有限公司 | A kind of face state appraisal procedure based on burst mode |
| CN108851833A (en) * | 2018-06-01 | 2018-11-23 | 辽宁工程技术大学 | Smart pier glass and its training method based on machine learning training algorithm |
| CN109101870A (en) * | 2018-06-15 | 2018-12-28 | 深圳市赛亿科技开发有限公司 | Intelligent mirror and its control method, computer readable storage medium |
| CN109523334A (en) * | 2018-08-30 | 2019-03-26 | 新我科技(广州)有限公司 | Box between a kind of cosmetics intelligent shopping guide system, cosmetics intelligent shopping guide method and intelligent cosmetic |
| CN109618045A (en) * | 2018-11-27 | 2019-04-12 | Oppo广东移动通信有限公司 | Electronic device, information-pushing method and Related product |
| CN109614900A (en) * | 2018-11-29 | 2019-04-12 | 深圳和而泰数据资源与云技术有限公司 | Image detecting method and device |
| CN109886881A (en) * | 2019-01-10 | 2019-06-14 | 中国科学院自动化研究所 | Face dressing minimizing technology |
| CN109886881B (en) * | 2019-01-10 | 2021-03-09 | 中国科学院自动化研究所 | Face makeup removal method |
| CN109919029A (en) * | 2019-01-31 | 2019-06-21 | 深圳和而泰数据资源与云技术有限公司 | Black eye kind identification method, device, computer equipment and storage medium |
| WO2021078037A1 (en) * | 2019-10-22 | 2021-04-29 | 华为技术有限公司 | Facial skin detection method and apparatus |
| CN111524080A (en) * | 2020-04-22 | 2020-08-11 | 杭州夭灵夭智能科技有限公司 | Face skin feature identification method, terminal and computer equipment |
| CN113971823A (en) * | 2020-07-24 | 2022-01-25 | 华为技术有限公司 | Method and electronic device for appearance analysis |
| CN113576421A (en) * | 2021-09-10 | 2021-11-02 | 广州帕克西软件开发有限公司 | Intelligent skin measuring method and device |
| CN113887483A (en) * | 2021-10-19 | 2022-01-04 | 杭州颜云科技有限公司 | Face pore detection method based on deep neural network |
| US11636600B1 (en) * | 2022-02-23 | 2023-04-25 | Lululab Inc. | Method and apparatus for detecting pores based on artificial neural network and visualizing the detected pores |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107437073A (en) | Face skin quality analysis method and system based on deep learning with generation confrontation networking | |
| Roesch et al. | FACSGen: A tool to synthesize emotional facial expressions through systematic manipulation of facial action units | |
| CN107123083B (en) | Face edit methods | |
| CN106650215A (en) | Skin type detection and individuation evaluation system and method based on cloud platform | |
| CN104331564B (en) | Adorn guidance method and terminal device based on terminal device | |
| Kortelainen et al. | Multimodal emotion recognition by combining physiological signals and facial expressions: a preliminary study | |
| CN110235169A (en) | Evaluation system of making up and its method of operating | |
| CN110400254A (en) | A kind of lipstick examination cosmetic method and device | |
| CN109278051A (en) | Exchange method and system based on intelligent robot | |
| CN106861012A (en) | User emotion adjusting method based on Intelligent bracelet under VR experience scenes | |
| CN113362422B (en) | Shadow robust makeup transfer system and method based on decoupling representation | |
| CN107437052A (en) | Blind date satisfaction computational methods and system based on micro- Expression Recognition | |
| CN105167290A (en) | Method for obtaining clothing matching index based on human body external image characteristic analysis | |
| Tagai et al. | The light-makeup advantage in facial processing: Evidence from event-related potentials | |
| Park et al. | An automatic virtual makeup scheme based on personal color analysis | |
| CN106937791A (en) | A kind of intelligent cosmetic beauty instrument and its intelligent tutoring system | |
| KR20190093040A (en) | Personal Color Analysis System with complex perception of the auditory and visual and fashion persona color matching method using the same | |
| KR20100096393A (en) | Apparatus and method for providing personal image in on-line interface | |
| JP2001292832A (en) | Method for classifying makeup color image and makeup color image map | |
| CN112819767A (en) | Image processing method, apparatus, device, storage medium, and program product | |
| Fitousi | How facial aging affects perceived gender: Insights from maximum likelihood conjoint measurement | |
| CN109885704A (en) | It is a kind of based on hair style identification intelligent hair style arrange care method and system | |
| Varshovi | Facial makeup detection using HSV color space and texture analysis | |
| CN111178560A (en) | AR technology-based hairdressing recommendation reservation system | |
| CN201654846U (en) | Color property testing and judging system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171205 |